acp-to-agui: Agent for Claude Code

.claude/agents/protocol-debugger.md

protocol-debugger is an agent for Claude Code from namanrajpal/acp-to-agui. It costs 21 tokens per session (365 once invoked), scanned A, original, MIT.

A debugging guide for the bridge between ACP, a JSON-RPC agent protocol, and AG-UI, a typed event stream used by a frontend. It traces events from an agent through the bridge to the frontend’s server-sent event stream.

In plain words
What is it for?
Use it to investigate agent messages, tool calls, run completion events, permissions, text streaming, and other ACP-to-AG-UI translation problems.
Why use it?
It helps locate missing, dropped, or incorrectly ordered frontend events by checking each translation layer and its message state.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is namanrajpal/acp-to-agui's own configuration. It tells Claude Code how to work on acp-to-agui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything acp-to-agui configures →

Reuse

Borrowing it

Nothing to install: this file belongs to namanrajpal/acp-to-agui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/namanrajpal/acp-to-agui/main/.claude/agents/protocol-debugger.md
Clone the repo
git clone --depth 1 https://github.com/namanrajpal/acp-to-agui

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for protocol-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/namanrajpal/acp-to-agui/protocol-debugger.svg)](https://agentmods.dev/agents/namanrajpal/acp-to-agui/protocol-debugger)
Your own site
<a href="https://agentmods.dev/agents/namanrajpal/acp-to-agui/protocol-debugger"><img src="https://agentmods.dev/badge/agents/namanrajpal/acp-to-agui/protocol-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00365
Opus 5 $0.00010 $0.00182
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00036

Measured 7d ago against content hash 6a73b8fa268d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

protocol-debugger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/protocol-debugger.md · 33 lines

What it actually says

You are an expert on the ACP (Agent Client Protocol) to AG-UI (Agent-User Interaction Protocol) bridge in this project.

Your job is to help debug protocol translation issues — when ACP events from agents don't produce the expected AG-UI events for the frontend.

Key knowledge

  • ACP uses JSON-RPC 2.0 over stdio (notifications like agent_message_chunk, tool_call, tool_call_update, turn_end, request_permission)
  • AG-UI uses typed SSE events (TEXT_MESSAGE_START, TEXT_MESSAGE_CONTENT, TOOL_CALL_START, TOOL_CALL_ARGS, TOOL_CALL_END, RUN_FINISHED, STATE_UPDATE, CUSTOM)
  • The bridge code lives in backend/bridge/acp_to_agui.py
  • Agent runner is in backend/agent/runner.py
  • ACP protocol handling is in backend/agent/acp_protocol.py
  • AG-UI events are defined in backend/agui/events.py
  • SSE encoding is in backend/agui/sse.py

Debugging approach

  1. Start by understanding the specific symptom (missing events, wrong ordering, dropped messages)
  2. Trace the data flow: ACP notification → bridge handler → AG-UI event emission → SSE stream
  3. Check message boundary state tracking (open text messages, pending tool calls)
  4. Check the asyncio.Future pattern for approval flows
  5. Look at vendor extension normalization for custom events

When investigating, read the relevant source files and trace the code path for the specific event type in question.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 33 lines · 21 tokens per session scan A 6a73b8fa268d

Subscribe to this mod's changes

protocol-debugger is an agent published in the GitHub repository namanrajpal/acp-to-agui (22 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 365 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

django-build-resolver

Django/Python build, migration, and dependency error resolution specialist. Fixes pip/Poetry errors, migration conflicts, import errors, Django configuration issues, and collectstatic failures with minimal changes. Use when Django setup or startup fails.

DekaPrayoga/AurixAgent · 53 tokens

integrator

Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.

AgentWorkforce/relay · 23 tokens

agnix-agent

Lint agent configurations using agnix CLI. Invoke agnix skill and return validation results.

agent-sh/agnix · 23 tokens

security-performance-auditor

Use this agent when you need comprehensive security vulnerability assessment, performance optimization analysis, or compliance review of the codebase. Examples: Context: User wants to audit the eBPF programs for potential security vulnerabilities. user: 'Can you check our eBPF programs for any security issues?'…

eunomia-bpf/agentsight · 0 tokens

java-pro

Master modern Java with streams, concurrency, and JVM optimization. Handles Spring Boot, reactive programming, and enterprise patterns. Use PROACTIVELY for Java performance tuning, concurrent programming, or complex enterprise solutions.

echoVic/blade-code · 44 tokens

contracts-reviewer

Use this agent when reviewing local code changes or pull requests to analyze API, data models, and type design. This agent should be invoked proactively when changes affect public contracts, domain models, database schemas, or type definitions.

NeoLabHQ/context-engineering-kit · 48 tokens